Training in progress, epoch 0

adapter_config.json

@@ -6,11 +6,12 @@
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.2,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -19,8 +20,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "k_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8852863f2c9742eb3027feafff2ff0449e38ee3ab52b2c954b74817016faecd3
-size 23641256
+oid sha256:6b96b7afc9e808c820eac2fb6b3a3e974238ba469987945ad1c6b5cd5da17f01
+size 33495872

runs/Nov08_00-13-33_QIPEI-LB02/events.out.tfevents.1731050015.QIPEI-LB02.580250.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9965daabdc2b36967b7fbd9cea92dec6d02982946488a6efc85db7dc87357d74
+size 25112

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21e326d5d48e8b8a254bfcdb7abcd06cae9c4a5bc7a706dcddcd164cdde2a368
+oid sha256:523b2280afc1baced207bf7d4bb287df73472218bd49873ff8da367b3a124236
 size 5560